Munich Personal RePEc Archive

Quasifiltering for time-series modeling

Tsyplakov, Alexander (2015): Quasifiltering for time-series modeling.


Download (588kB) | Preview


In the paper a method for constructing new varieties of time-series models is proposed. The idea is to start from an unobserved components model in a state-space form and use it as an inspiration for development of another time-series model, in which time-varying underlying variables are directly observed. The goal is to replace a state-space model with an intractable likelihood function by another model, for which the likelihood function can be written in a closed form. If state transition equation of the parent state-space model is linear Gaussian, then the resulting model would belong to the class of score driven model (aka GAS, DCS).

MPRA is a RePEc service hosted by
the Munich University Library in Germany.